RFR: 8312132: Add tracking of multiple address spaces in NMT [v120]

[Johan Sjölen]

On Thu, 30 May 2024 09:49:44 GMT, Johan Sjölen <jsjolen at openjdk.org> wrote:

>> Hi,
>> 
>> This PR introduces a new abstraction to NMT, named `MemoryFileTracker`. Today, NMT does not track any memory outside of the virtual memory address space. This means that if you allocated memory in something such as a memory-backed file and use `mmap` to map into that memory, then you'll have trouble reporting this to NMT. This is the situation that ZGC is in, and that is what this patch attempts to fix.
>> 
>> ## `MemoryFileTracker`
>> 
>> The `MemoryFileTracker` adds the ability of adding new virtual memory address spaces to NMT and committing memory to these, the basic API is:
>> 
>> ```c++
>>     static MemoryFile* make_device(const char* descriptive_name);
>>     static void free_device(MemoryFile* device);
>> 
>>     static void allocate_memory(MemoryFile* device, size_t offset, size_t size,
>>                                 MEMFLAGS flag, const NativeCallStack& stack);
>>     static void free_memory(MemoryFile* device, size_t offset, size_t size);
>> 
>> 
>> It is easiest to see how this is used by looking at what ZGC's `ZNMT` class does:
>> 
>> ```c++
>> void ZNMT::reserve(zaddress_unsafe start, size_t size) {
>>   MemTracker::record_virtual_memory_reserve((address)start, size, CALLER_PC, mtJavaHeap);
>> }
>> void ZNMT::commit(zoffset offset, size_t size) {
>>   MemTracker::allocate_memory_in(ZNMT::_device, static_cast<size_t>(offset), size, mtJavaHeap, CALLER_PC);
>> }
>> void ZNMT::uncommit(zoffset offset, size_t size) {
>>   MemTracker::free_memory_in(ZNMT::_device, (size_t)offset, size);
>> }
>> 
>> void ZNMT::map(zaddress_unsafe addr, size_t size, zoffset offset) {
>>   // NMT doesn't track mappings at the moment.
>> }
>> void ZNMT::unmap(zaddress_unsafe addr, size_t size) {
>>   // NMT doesn't track mappings at the moment.
>> }
>> 
>> 
>> As you can see, any mapping between reserved regions and device-allocated memory is not recorded in NMT. This means that in detailed mode you only get reserved regions printed for the reserved memory, the device-allocated memory is reported separately. When performing summary reporting any memory allocated via these devices is added to the corresponding `MEMFLAGS` as `committed` memory. 
>> 
>> This patch is also acting as a base on which we deploy multiple new backend ideas to NMT. These ideas are:
>> 
>> 1. Implement VMA tracking using a balanced binary tree approach. Today's `VirtualMemoryTracker`'s usage of linked lists is slow and brittle, we'd like to move away from it. Our Treap-based approach in this patch gives a performance bo...
>
> Johan Sjölen has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Device shouldn't be nullptr

Tier 1-3 entirely green except for an issue on debug builds where we assert that file != nullptr before we check whether NMT is enabled. If NMT is disabled, then `register_file` will return nullptr, which will cause those asserts to be hit. I've moved the asserts.

I've changed the summary semantics so that all commits in `MemoryFileTracker` is both reserved and committed. This means that we both reserve address ranges in the 'ordinary' virtual memory space, and in the MemoryFile. Both of these are accounted for under the same memory flag in summary mode. This is a form of close-to-but-not-really double-accounting. My question is: Is this acceptable? I'm asking the ZGC people about this now.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/18289#issuecomment-2139537892